arXiv research

VHGM-MAE generates synthetic humans from healthcare data.

The paper explores MAE as a loss function for DNN vector-to-vector regression, proving its advantages over MSE.

Theoretical analysis of vision transformers' performance with MAE and CL objectives.

In this work, we study robust deep learning against abnormal training data from the perspective of example weighting built in empirical loss functions, i.e., gradient magnitude with respect to logits, an angle that is not thoroughly studied so far. Consequently, we have two key findings: (1) Mean Absolute Error (MAE) D…

Paper proposes a new metric to evaluate survival models, especially for censored data.

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression. We show that universal consistency of Empirical Risk Minimiza…

Method finds MAEs on contactified para-Kähler manifolds.

We study the geometry of multidimensional scalar $2^{nd}$ order PDEs (i.e. PDEs with $n$ independent variables) with one unknown function, viewed as hypersurfaces $\mathcal{E}$ in the Lagrangian Grassmann bundle $M^{(1)}$ over a $(2n+1)$-dimensional contact manifold $(M,\mathcal{C})$. We develop the theory of character…

We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology. It uses dual recurrent neural network controllers, inside the encoder and solver, respectively, that interface with a shared memory module a…

Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets. Moreover, due to DNNs' rich capacity, errors in training labels can hamper performance. …

We propose a new approach for Collaborative Filtering which is based on Boolean Matrix Factorisation (BMF) and Formal Concept Analysis. In a series of experiments on real data (Movielens dataset) we compare the approach with the SVD- and NMF-based algorithms in terms of Mean Average Error (MAE). One of the experimental…

CRATE-MAE learns structured representations from unlabeled data.

Proposes a proportional masking strategy for better tabular data imputation.

LSTM models outperform traditional ARIMA in S&P 500 forecasting.

Study benchmarks classical models over quantum in DeFi yield prediction.

Objective: Predict individual septic children's personalized physiologic responses to vasoactive titrations by training a Recurrent Neural Network (RNN) using EMR data. Materials and Methods: This study retrospectively analyzed EMR of patients admitted to a pediatric ICU from 2009 to 2017. Data included charted time se…

A new modal autoencoder improves feature extraction by constraining the decoder.

PIVOT bridges Black-Scholes price and implied volatility spaces via a differentiable layer.

Study uses satellite and lidar data to map forest height and biomass in France.

Proposes a new loss function for learning with noisy labels.

New findings challenge the importance of forecast accuracy in battery storage optimization, highlighting the role of rank correlation instead.

Proposes MGCE for improved classification performance.

The paper bounds the mean absolute error in DNN vector-to-vector regression.

We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model …

New method estimates extreme outcomes in heavy-tailed data, breaking circular dependence.

A new Bayesian model improves forecasting for intermittent demand.

Cold-start PV forecasting uses synthetic histories to train time-series foundation models.

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression. We also show that, under some asumptions, universal consisten…

Models predict probabilities of causation from limited data.

Automated anomaly detection is essential for managing information and communications technology (ICT) systems to maintain reliable services with minimum burden on operators. For detecting varying and continually emerging anomalies as differences from normal states, learning normal relationships inherent among cross-dom…

Optimizes shortfall risk using gradient-based methods.

This paper evaluates forecast quality in electricity markets beyond traditional accuracy measures.

MoCA uses a novel autoencoder to analyze multi-modal health data.

In construction projects, estimation of the settlement of fine-grained soils is of critical importance, and yet is a challenging task. The coefficient of consolidation for the compression index (Cc) is a key parameter in modeling the settlement of fine-grained soil layers. However, the estimation of this parameter is c…

ANN model predicts zinc leaching filter cake moisture accurately.

The uncertainties in future Bitcoin price make it difficult to accurately predict the price of Bitcoin. Accurately predicting the price for Bitcoin is therefore important for decision-making process of investors and market players in the cryptocurrency market. Using historical data from 01/01/2012 to 16/08/2019, machin…

Given the wide success of convolutional neural networks (CNNs) applied to natural images, researchers have begun to apply them to neuroimaging data. To date, however, exploration of novel CNN architectures tailored to neuroimaging data has been limited. Several recent works fail to leverage the 3D structure of the brai…

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We prove the existence of an optimal MAPE model and we show the universal consistency of Empirical Risk Minimization based on the MAPE. We also show that finding the best model under…

For quantitative structure-property relationship (QSPR) studies in chemoinformatics, it is important to get interpretable relationship between chemical properties and chemical features. However, the predictive power and interpretability of QSPR models are usually two different objectives that are difficult to achieve s…

New methods improve insurance data quality for catastrophic events.

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in th…

A neural network solves Black-Scholes PDE for option pricing with uncertainty quantification.

This paper models yearly exchange rates between USD/KZT, EUR/KZT and SGD/KZT, and compares the actual data with developed forecasts using time series analysis over the period from 2006 to 2014. The official yearly data of National Bank of the Republic of Kazakhstan is used for present study. The main goal of this paper…

MMformer improves forecasting of environmental time series data.

This study compares deep learning and statistical models for stock price forecasting.

Share prices of financial companies from the S&P 500 list have been modeled by a linear function of consumer price indices in the USA. The Johansen and Engle-Granger tests for cointegration both demonstrated the presence of an equilibrium long-term relation between observed and predicted time series. Econometrically, t…

Disease progression modeling (DPM) using longitudinal data is a challenging machine learning task. Existing DPM algorithms neglect temporal dependencies among measurements, make parametric assumptions about biomarker trajectories, do not model multiple biomarkers jointly, and need an alignment of subjects' trajectories…

Satellite images improve real-estate price predictions.